songlin/d3roma
A diffusion model-based stereo depth estimation framework that can predict and restore noisy depth maps for transparent and specular surfaces
This project helps robots perceive the depth of tricky objects like transparent bottles or shiny metal surfaces, which often confuse standard depth sensors. It takes in stereo images or RGB+raw depth data and outputs a precise depth map and 3D point cloud of the environment. Roboticists, automation engineers, and anyone developing robotic systems for manipulating diverse objects in real-world settings would use this.
No commits in the last 6 months.
Use this if your robotic system struggles with accurately sensing the depth of transparent or specular objects, hindering tasks like grasping or assembly.
Not ideal if your application primarily deals with matte, opaque objects where standard depth sensors already perform well.
Stars
89
Forks
9
Language
Python
License
—
Category
Last pushed
Feb 27, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/songlin/d3roma"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jayin92/Skyfall-GS
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
Tencent-Hunyuan/Hunyuan3D-2
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
ActiveVisionLab/gaussctrl
[ECCV 2024] GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
caiyuanhao1998/Open-DiffusionGS
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D...
deepseek-ai/DreamCraft3D
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with...